© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 57917
    Prev
    Next
    INDEX
    Explanations

    socket addresses

    np_max-act · gemini-2.0-flash

    The neuron fires on C/C++ include directives for networking headers (e.g. `<netinet/in.h>`, `<arpa/inet.h>`, `<netdb.h>`, etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Bern
    -0.06
     Stuff
    -0.06
    empresa
    -0.06
    geh
    -0.06
     Readers
    -0.06
     dohod
    -0.06
    普
    -0.06
    781
    -0.06
    egative
    -0.06
    907
    -0.06
    POSITIVE LOGITS
     Trout
    0.07
     brackets
    0.06
     aşam
    0.06
    _Msp
    0.06
    ้าส
    0.06
     nuôi
    0.06
    ные
    0.06
    LookAndFeel
    0.06
     unexpected
    0.06
     파일
    0.06
    Activations Density 0.004%

    No Known Activations